© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5170
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and their relationships within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     III
    -0.38
    庁
    -0.37
    III
    -0.31
    iii
    -0.31
    thalene
    -0.29
     ternary
    -0.28
     esternos
    -0.27
     auxquelles
    -0.27
     iii
    -0.27
     three
    -0.26
    POSITIVE LOGITS
    évaluateur
    0.64
    RegressionTest
    0.59
    SourceChecksum
    0.57
    цездатний
    0.56
    emlrt
    0.55
    IndentedString
    0.55
     ComVisible
    0.54
    Interpre
    0.53
    ACHUSET
    0.53
    webElementXpaths
    0.52
    Activations Density 0.885%

    No Known Activations